mercurial/exewrapper.c

revlog: use compression engine API for compression

This commit swaps in the just-added revlog compressor API into
the revlog class.

Instead of implementing zlib compression inline in compress(), we
now store a cached-on-first-use revlog compressor on each revlog
instance and invoke its "compress()" method.

As part of this, revlog.compress() has been refactored a bit to use
a cleaner code flow and modern formatting (e.g. avoiding
parenthesis around returned tuples).

On a mozilla-unified repo, here are the "compress" times for a few
commands:

$ hg perfrevlogchunks -c
! wall 5.772450 comb 5.780000 user 5.780000 sys 0.000000 (best of 3)
! wall 5.795158 comb 5.790000 user 5.790000 sys 0.000000 (best of 3)

$ hg perfrevlogchunks -m
! wall 9.975789 comb 9.970000 user 9.970000 sys 0.000000 (best of 3)
! wall 10.019505 comb 10.010000 user 10.010000 sys 0.000000 (best of 3)

Compression times did seem to slow down just a little. There are
360,210 changelog revisions and 359,342 manifest revisions. For the
changelog, mean time to compress a revision increased from ~16.025us to
~16.088us. That's basically a function call or an attribute lookup. I
suppose this is the price you pay for abstraction. It's so low that
I'm not concerned.

/*
 exewrapper.c - wrapper for calling a python script on Windows

 Copyright 2012 Adrian Buehlmann <[e-mail]> and others

 This software may be used and distributed according to the terms of the
 GNU General Public License version 2 or any later version.
*/

#include <stdio.h>
#include <windows.h>

#include "hgpythonlib.h"

#ifdef __GNUC__
int strcat_s(char *d, size_t n, const char *s)
{
	return !strncat(d, s, n);
}
int strcpy_s(char *d, size_t n, const char *s)
{
	return !strncpy(d, s, n);
}
#endif


static char pyscript[MAX_PATH + 10];
static char pyhome[MAX_PATH + 10];
static char envpyhome[MAX_PATH + 10];
static char pydllfile[MAX_PATH + 10];

int main(int argc, char *argv[])
{
	char *p;
	int ret;
	int i;
	int n;
	char **pyargv;
	WIN32_FIND_DATA fdata;
	HANDLE hfind;
	const char *err;
	HMODULE pydll;
	void (__cdecl *Py_SetPythonHome)(char *home);
	int (__cdecl *Py_Main)(int argc, char *argv[]);

	if (GetModuleFileName(NULL, pyscript, sizeof(pyscript)) == 0)
	{
		err = "GetModuleFileName failed";
		goto bail;
	}

	p = strrchr(pyscript, '.');
	if (p == NULL) {
		err = "malformed module filename";
		goto bail;
	}
	*p = 0; /* cut trailing ".exe" */
	strcpy_s(pyhome, sizeof(pyhome), pyscript);

	hfind = FindFirstFile(pyscript, &fdata);
	if (hfind != INVALID_HANDLE_VALUE) {
		/* pyscript exists, close handle */
		FindClose(hfind);
	} else {
		/* file pyscript isn't there, take <pyscript>exe.py */
		strcat_s(pyscript, sizeof(pyscript), "exe.py");
	}

	pydll = NULL;
	/*
	We first check, that environment variable PYTHONHOME is *not* set.
	This just mimicks the behavior of the regular python.exe, which uses
	PYTHONHOME to find its installation directory (if it has been set).
	Note: Users of HackableMercurial are expected to *not* set PYTHONHOME!
	*/
	if (GetEnvironmentVariable("PYTHONHOME", envpyhome,
				   sizeof(envpyhome)) == 0)
	{
		/*
		Environment var PYTHONHOME is *not* set. Let's see if we are
		running inside a HackableMercurial.
		*/

		p = strrchr(pyhome, '\\');
		if (p == NULL) {
			err = "can't find backslash in module filename";
			goto bail;
		}
		*p = 0; /* cut at directory */

		/* check for private Python of HackableMercurial */
		strcat_s(pyhome, sizeof(pyhome), "\\hg-python");

		hfind = FindFirstFile(pyhome, &fdata);
		if (hfind != INVALID_HANDLE_VALUE) {
			/* path pyhome exists, let's use it */
			FindClose(hfind);
			strcpy_s(pydllfile, sizeof(pydllfile), pyhome);
			strcat_s(pydllfile, sizeof(pydllfile),
				 "\\" HGPYTHONLIB ".dll");
			pydll = LoadLibrary(pydllfile);
			if (pydll == NULL) {
				err = "failed to load private Python DLL "
				      HGPYTHONLIB ".dll";
				goto bail;
			}
			Py_SetPythonHome = (void*)GetProcAddress(pydll,
							"Py_SetPythonHome");
			if (Py_SetPythonHome == NULL) {
				err = "failed to get Py_SetPythonHome";
				goto bail;
			}
			Py_SetPythonHome(pyhome);
		}
	}

	if (pydll == NULL) {
		pydll = LoadLibrary(HGPYTHONLIB ".dll");
		if (pydll == NULL) {
			err = "failed to load Python DLL " HGPYTHONLIB ".dll";
			goto bail;
		}
	}

	Py_Main = (void*)GetProcAddress(pydll, "Py_Main");
	if (Py_Main == NULL) {
		err = "failed to get Py_Main";
		goto bail;
	}

	/*
	Only add the pyscript to the args, if it's not already there. It may
	already be there, if the script spawned a child process of itself, in
	the same way as it got called, that is, with the pyscript already in
	place. So we optionally accept the pyscript as the first argument
	(argv[1]), letting our exe taking the role of the python interpreter.
	*/
	if (argc >= 2 && strcmp(argv[1], pyscript) == 0) {
		/*
		pyscript is already in the args, so there is no need to copy
		the args and we can directly call the python interpreter with
		the original args.
		*/
		return Py_Main(argc, argv);
	}

	/*
	Start assembling the args for the Python interpreter call. We put the
	name of our exe (argv[0]) in the position where the python.exe
	canonically is, and insert the pyscript next.
	*/
	pyargv = malloc((argc + 5) * sizeof(char*));
	if (pyargv == NULL) {
		err = "not enough memory";
		goto bail;
	}
	n = 0;
	pyargv[n++] = argv[0];
	pyargv[n++] = pyscript;

	/* copy remaining args from the command line */
	for (i = 1; i < argc; i++)
		pyargv[n++] = argv[i];
	/* argv[argc] is guaranteed to be NULL, so we forward that guarantee */
	pyargv[n] = NULL;

	ret = Py_Main(n, pyargv); /* The Python interpreter call */

	free(pyargv);
	return ret;

bail:
	fprintf(stderr, "abort: %s\n", err);
	return 255;
}